Conceptio
›
Archive
›
arXiv (OAI Expanded)
arXiv (OAI Expanded)
open access
ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models
Jiang, Wenzheng et al.
arXiv (OAI Expanded) · Papers · License: Open Access
Open Source ↗
Direct PDF ↓
k.6.5
artificial intelligence, i.2.0; k.6.5
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Related documents
Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty
#965975
Building a research-software catalog with a coding agent: from hackathon prototype to public deployment
#965976
Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models
#965979
Record
· ID 661223
Retrieved via
Conceptio
— every document is proof-bundled with source, license, and retrieval metadata.